From the course: PyTorch Essential Training: Deep Learning
Join today to access over 24,900 courses taught by industry experts.
Linear algebra operations
From the course: PyTorch Essential Training: Deep Learning
Linear algebra operations
- [Instructor] Linear algebra is used heavily in deep learning computations, from different optimization algorithms to gradient descent. Let's explore the most important ones. PyTorch has a module called torch lineal that contains a set of built-in linear algebra functions that are mostly based on the basic linear algebra, subprograms or Blast and Linear algebra package or APEC standardized libraries. You can find a complete list of functions on the following PyTorch linear algebra documentation page. If you have already mastered Numpy, you will quickly learn these functions as most of the functions from Numpy's linear algebra module are the same, but they're extended with accelerator and L2 grad support. Only a few of the functions will be completely new. If you haven't explored the linear algebra capabilities of Numpy, you can take my course, Numpy Essential Training. We have already imported PyTorch. The first useful function performs matrix products of two tensors, and it's called…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.